Energy Dataset¶
Exercise 1¶
In [ ]:
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px
In [ ]:
data = pd.read_csv('https://raw.githubusercontent.com/PacktWorkshops/The-Data-Analysis-Workshop/master/Chapter09/Datasets/energydata_complete.csv')
In [3]:
data.head()
Out[3]:
In [4]:
data.isnull().sum()
Out[4]:
In [ ]:
df1 = data.rename(columns = {
'date' : 'date_time',
'Appliances' : 'a_energy',
'lights' : 'l_energy',
'T1' : 'kitchen_temp',
'RH_1' : 'kitchen_hum',
'T2' : 'liv_temp',
'RH_2' : 'liv_hum',
'T3' : 'laun_temp',
'RH_3' : 'laun_hum',
'T4' : 'off_temp',
'RH_4' : 'off_hum',
'T5' : 'bath_temp',
'RH_5' : 'bath_hum',
'T6' : 'out_b_temp',
'RH_6' : 'out_b_hum',
'T7' : 'iron_temp',
'RH_7' : 'iron_hum',
'T8' : 'teen_temp',
'RH_8' : 'teen_hum',
'T9' : 'par_temp',
'RH_9' : 'par_hum',
'T_out' : 'out_temp',
'Press_mm_hg' : 'out_press',
'RH_out' : 'out_hum',
'Windspeed' : 'wind',
'Visibility' : 'visibility',
'Tdewpoint' : 'dew_point',
'rv1' : 'rv1',
'rv2' : 'rv2'
})
In [6]:
df1.head()
Out[6]:
In [7]:
df1.tail()
Out[7]:
In [8]:
df1.describe()
Out[8]:
In [ ]:
In [ ]:
## Exercise 2
In [ ]:
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px
In [ ]:
data = pd.read_csv('https://raw.githubusercontent.com/PacktWorkshops/The-Data-Analysis-Workshop/master/Chapter09/Datasets/energydata_complete.csv')
In [3]:
data.head()
Out[3]:
In [4]:
data.isnull().sum()
Out[4]:
In [ ]:
df1 = data.rename(columns = {
'date' : 'date_time',
'Appliances' : 'a_energy',
'lights' : 'l_energy',
'T1' : 'kitchen_temp',
'RH_1' : 'kitchen_hum',
'T2' : 'liv_temp',
'RH_2' : 'liv_hum',
'T3' : 'laun_temp',
'RH_3' : 'laun_hum',
'T4' : 'off_temp',
'RH_4' : 'off_hum',
'T5' : 'bath_temp',
'RH_5' : 'bath_hum',
'T6' : 'out_b_temp',
'RH_6' : 'out_b_hum',
'T7' : 'iron_temp',
'RH_7' : 'iron_hum',
'T8' : 'teen_temp',
'RH_8' : 'teen_hum',
'T9' : 'par_temp',
'RH_9' : 'par_hum',
'T_out' : 'out_temp',
'Press_mm_hg' : 'out_press',
'RH_out' : 'out_hum',
'Windspeed' : 'wind',
'Visibility' : 'visibility',
'Tdewpoint' : 'dew_point',
'rv1' : 'rv1',
'rv2' : 'rv2'
})
In [6]:
df1.head()
Out[6]:
In [7]:
df1.tail()
Out[7]:
In [8]:
df1.describe()
Out[8]:
Exercise 9.02: Analyzing the Light Energy Consumption Column
In [9]:
lights_box = sns.boxplot(df1.l_energy)
In [ ]:
l = [0, 10, 20, 30, 40, 50, 60, 70]
In [ ]:
counts = []
In [ ]:
for i in l:
a = (df1.l_energy == i).sum()
counts.append(a)
In [13]:
counts
Out[13]:
In [14]:
lights = sns.barplot(x = l, y = counts)
lights.set_xlabel('Energy Consumed by Lights')
lights.set_ylabel('Number of Lights')
lights.set_title('Distribution of Energy Consumed by Lights')
Out[14]:
In [15]:
((df1.l_energy == 0).sum() / (df1.shape[0])) * 100
Out[15]:
In [ ]:
new_data = df1
In [ ]:
new_data.drop(['l_energy'], axis = 1, inplace = True)
In [18]:
new_data.head()
Out[18]:
In [ ]:
In [ ]:
## Exercise 3
In [ ]:
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px
In [ ]:
data = pd.read_csv('https://raw.githubusercontent.com/PacktWorkshops/The-Data-Analysis-Workshop/master/Chapter09/Datasets/energydata_complete.csv')
In [3]:
data.head()
Out[3]:
In [4]:
data.isnull().sum()
Out[4]:
In [ ]:
df1 = data.rename(columns = {
'date' : 'date_time',
'Appliances' : 'a_energy',
'lights' : 'l_energy',
'T1' : 'kitchen_temp',
'RH_1' : 'kitchen_hum',
'T2' : 'liv_temp',
'RH_2' : 'liv_hum',
'T3' : 'laun_temp',
'RH_3' : 'laun_hum',
'T4' : 'off_temp',
'RH_4' : 'off_hum',
'T5' : 'bath_temp',
'RH_5' : 'bath_hum',
'T6' : 'out_b_temp',
'RH_6' : 'out_b_hum',
'T7' : 'iron_temp',
'RH_7' : 'iron_hum',
'T8' : 'teen_temp',
'RH_8' : 'teen_hum',
'T9' : 'par_temp',
'RH_9' : 'par_hum',
'T_out' : 'out_temp',
'Press_mm_hg' : 'out_press',
'RH_out' : 'out_hum',
'Windspeed' : 'wind',
'Visibility' : 'visibility',
'Tdewpoint' : 'dew_point',
'rv1' : 'rv1',
'rv2' : 'rv2'
})
In [6]:
df1.head()
Out[6]:
In [7]:
df1.tail()
Out[7]:
In [8]:
df1.describe()
Out[8]:
In [9]:
lights_box = sns.boxplot(df1.l_energy)
In [ ]:
l = [0, 10, 20, 30, 40, 50, 60, 70]
In [ ]:
counts = []
In [ ]:
for i in l:
a = (df1.l_energy == i).sum()
counts.append(a)
In [13]:
counts
Out[13]:
In [14]:
lights = sns.barplot(x = l, y = counts)
lights.set_xlabel('Energy Consumed by Lights')
lights.set_ylabel('Number of Lights')
lights.set_title('Distribution of Energy Consumed by Lights')
Out[14]:
In [15]:
((df1.l_energy == 0).sum() / (df1.shape[0])) * 100
Out[15]:
In [ ]:
new_data = df1
In [ ]:
new_data.drop(['l_energy'], axis = 1, inplace = True)
In [18]:
new_data.head()
Out[18]:
In [19]:
app_box = sns.boxplot(new_data.a_energy)
In [20]:
out = (new_data['a_energy'] > 200).sum()
out
Out[20]:
In [21]:
(out/19735) * 100
Out[21]:
In [22]:
out_e = (new_data['a_energy'] > 950).sum()
out_e
Out[22]:
In [23]:
(out_e/19735) * 100
Out[23]:
In [ ]:
energy = new_data[(new_data['a_energy'] <= 200)]
In [25]:
energy.describe()
Out[25]:
Exercise 9.03: Performing Feature Engineering
In [ ]:
new_en = energy
In [ ]:
new_en['date_time'] = pd.to_datetime(new_en.date_time, format = '%Y-%m-%d %H:%M:%S')
In [28]:
new_en.head()
Out[28]:
In [ ]:
new_en.insert(loc = 1, column = 'month', value = new_en.date_time.dt.month)
In [ ]:
new_en.insert(loc = 2, column = 'day', value = (new_en.date_time.dt.dayofweek)+1)
In [31]:
new_en.head()
Out[31]:
In [ ]:
In [ ]:
## Exercise 4
In [ ]:
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px
In [ ]:
data = pd.read_csv('https://raw.githubusercontent.com/PacktWorkshops/The-Data-Analysis-Workshop/master/Chapter09/Datasets/energydata_complete.csv')
In [3]:
data.head()
Out[3]:
In [4]:
data.isnull().sum()
Out[4]:
In [ ]:
df1 = data.rename(columns = {
'date' : 'date_time',
'Appliances' : 'a_energy',
'lights' : 'l_energy',
'T1' : 'kitchen_temp',
'RH_1' : 'kitchen_hum',
'T2' : 'liv_temp',
'RH_2' : 'liv_hum',
'T3' : 'laun_temp',
'RH_3' : 'laun_hum',
'T4' : 'off_temp',
'RH_4' : 'off_hum',
'T5' : 'bath_temp',
'RH_5' : 'bath_hum',
'T6' : 'out_b_temp',
'RH_6' : 'out_b_hum',
'T7' : 'iron_temp',
'RH_7' : 'iron_hum',
'T8' : 'teen_temp',
'RH_8' : 'teen_hum',
'T9' : 'par_temp',
'RH_9' : 'par_hum',
'T_out' : 'out_temp',
'Press_mm_hg' : 'out_press',
'RH_out' : 'out_hum',
'Windspeed' : 'wind',
'Visibility' : 'visibility',
'Tdewpoint' : 'dew_point',
'rv1' : 'rv1',
'rv2' : 'rv2'
})
In [6]:
df1.head()
Out[6]:
In [7]:
df1.tail()
Out[7]:
In [8]:
df1.describe()
Out[8]:
In [9]:
lights_box = sns.boxplot(df1.l_energy)
In [ ]:
l = [0, 10, 20, 30, 40, 50, 60, 70]
In [ ]:
counts = []
In [ ]:
for i in l:
a = (df1.l_energy == i).sum()
counts.append(a)
In [13]:
counts
Out[13]:
In [14]:
lights = sns.barplot(x = l, y = counts)
lights.set_xlabel('Energy Consumed by Lights')
lights.set_ylabel('Number of Lights')
lights.set_title('Distribution of Energy Consumed by Lights')
Out[14]:
In [15]:
((df1.l_energy == 0).sum() / (df1.shape[0])) * 100
Out[15]:
In [ ]:
new_data = df1
In [ ]:
new_data.drop(['l_energy'], axis = 1, inplace = True)
In [18]:
new_data.head()
Out[18]:
In [19]:
app_box = sns.boxplot(new_data.a_energy)
In [20]:
out = (new_data['a_energy'] > 200).sum()
out
Out[20]:
In [21]:
(out/19735) * 100
Out[21]:
In [22]:
out_e = (new_data['a_energy'] > 950).sum()
out_e
Out[22]:
In [23]:
(out_e/19735) * 100
Out[23]:
In [ ]:
energy = new_data[(new_data['a_energy'] <= 200)]
In [25]:
energy.describe()
Out[25]:
In [ ]:
new_en = energy
In [ ]:
new_en['date_time'] = pd.to_datetime(new_en.date_time, format = '%Y-%m-%d %H:%M:%S')
In [28]:
new_en.head()
Out[28]:
In [ ]:
new_en.insert(loc = 1, column = 'month', value = new_en.date_time.dt.month)
In [ ]:
new_en.insert(loc = 2, column = 'day', value = (new_en.date_time.dt.dayofweek)+1)
In [31]:
new_en.head()
Out[31]:
Exercise 9.04: Visualizing the Dataset
In [ ]:
import plotly.graph_objs as go
In [ ]:
app_date = go.Scatter(x = new_en.date_time, mode = "lines", y = new_en.a_energy)
In [ ]:
layout = go.Layout(title = 'Appliance Energy Consumed by Date', xaxis = dict(title='Date'), yaxis = dict(title='Wh'))
In [ ]:
fig = go.Figure(data = [app_date], layout = layout)
In [37]:
fig.show()
In [ ]:
app_mon = new_en.groupby(by = ['month'], as_index = False)['a_energy'].sum()
In [39]:
app_mon
Out[39]:
In [40]:
app_mon.sort_values(by = 'a_energy', ascending = False).head()
Out[40]:
In [44]:
plt.subplots(figsize = (15, 6))
am = sns.barplot(app_mon.month, app_mon.a_energy)
plt.xlabel('Month')
plt.ylabel('Energy Consumed by Appliances')
plt.title('Total Energy Consumed by Appliances per Month')
plt.show()
In [ ]:
In [ ]:
## Exercise 5
In [ ]:
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px
In [ ]:
data = pd.read_csv('https://raw.githubusercontent.com/PacktWorkshops/The-Data-Analysis-Workshop/master/Chapter09/Datasets/energydata_complete.csv')
In [3]:
data.head()
Out[3]:
In [4]:
data.isnull().sum()
Out[4]:
In [ ]:
df1 = data.rename(columns = {
'date' : 'date_time',
'Appliances' : 'a_energy',
'lights' : 'l_energy',
'T1' : 'kitchen_temp',
'RH_1' : 'kitchen_hum',
'T2' : 'liv_temp',
'RH_2' : 'liv_hum',
'T3' : 'laun_temp',
'RH_3' : 'laun_hum',
'T4' : 'off_temp',
'RH_4' : 'off_hum',
'T5' : 'bath_temp',
'RH_5' : 'bath_hum',
'T6' : 'out_b_temp',
'RH_6' : 'out_b_hum',
'T7' : 'iron_temp',
'RH_7' : 'iron_hum',
'T8' : 'teen_temp',
'RH_8' : 'teen_hum',
'T9' : 'par_temp',
'RH_9' : 'par_hum',
'T_out' : 'out_temp',
'Press_mm_hg' : 'out_press',
'RH_out' : 'out_hum',
'Windspeed' : 'wind',
'Visibility' : 'visibility',
'Tdewpoint' : 'dew_point',
'rv1' : 'rv1',
'rv2' : 'rv2'
})
In [6]:
df1.head()
Out[6]:
In [7]:
df1.tail()
Out[7]:
In [8]:
df1.describe()
Out[8]:
In [9]:
lights_box = sns.boxplot(df1.l_energy)
In [ ]:
l = [0, 10, 20, 30, 40, 50, 60, 70]
In [ ]:
counts = []
In [ ]:
for i in l:
a = (df1.l_energy == i).sum()
counts.append(a)
In [13]:
counts
Out[13]:
In [14]:
lights = sns.barplot(x = l, y = counts)
lights.set_xlabel('Energy Consumed by Lights')
lights.set_ylabel('Number of Lights')
lights.set_title('Distribution of Energy Consumed by Lights')
Out[14]:
In [15]:
((df1.l_energy == 0).sum() / (df1.shape[0])) * 100
Out[15]:
In [ ]:
new_data = df1
In [ ]:
new_data.drop(['l_energy'], axis = 1, inplace = True)
In [18]:
new_data.head()
Out[18]:
In [19]:
app_box = sns.boxplot(new_data.a_energy)
In [20]:
out = (new_data['a_energy'] > 200).sum()
out
Out[20]:
In [21]:
(out/19735) * 100
Out[21]:
In [22]:
out_e = (new_data['a_energy'] > 950).sum()
out_e
Out[22]:
In [23]:
(out_e/19735) * 100
Out[23]:
In [ ]:
energy = new_data[(new_data['a_energy'] <= 200)]
In [25]:
energy.describe()
Out[25]:
In [ ]:
new_en = energy
In [ ]:
new_en['date_time'] = pd.to_datetime(new_en.date_time, format = '%Y-%m-%d %H:%M:%S')
In [28]:
new_en.head()
Out[28]:
In [ ]:
new_en.insert(loc = 1, column = 'month', value = new_en.date_time.dt.month)
In [ ]:
new_en.insert(loc = 2, column = 'day', value = (new_en.date_time.dt.dayofweek)+1)
In [31]:
new_en.head()
Out[31]:
In [ ]:
import plotly.graph_objs as go
In [ ]:
app_date = go.Scatter(x = new_en.date_time, mode = "lines", y = new_en.a_energy)
In [ ]:
layout = go.Layout(title = 'Appliance Energy Consumed by Date', xaxis = dict(title='Date'), yaxis = dict(title='Wh'))
In [ ]:
fig = go.Figure(data = [app_date], layout = layout)
In [37]:
fig.show()
In [ ]:
app_mon = new_en.groupby(by = ['month'], as_index = False)['a_energy'].sum()
In [39]:
app_mon
Out[39]:
In [40]:
app_mon.sort_values(by = 'a_energy', ascending = False).head()
Out[40]:
In [44]:
plt.subplots(figsize = (15, 6))
am = sns.barplot(app_mon.month, app_mon.a_energy)
plt.xlabel('Month')
plt.ylabel('Energy Consumed by Appliances')
plt.title('Total Energy Consumed by Appliances per Month')
plt.show()
In [45]:
app_day = new_en.groupby(by = ['day'], as_index = False)['a_energy'].sum()
app_day
Out[45]:
In [46]:
app_day.sort_values(by = 'a_energy', ascending = False)
Out[46]:
In [47]:
plt.subplots(figsize = (15, 6))
ad = sns.barplot(app_day.day, app_day.a_energy)
plt.xlabel('Day of the Week')
plt.ylabel('Energy Consumed by Appliances')
plt.title('Total Energy Consumed by Appliances')
plt.show()
Exercise 9.05: Plotting distributions of the temperature columns
In [ ]:
col_temp = ['kitchen_temp', 'liv_temp', 'laun_temp', 'off_temp',
'bath_temp', 'out_b_temp', 'iron_temp', 'teen_temp', 'par_temp']
In [ ]:
temp = new_en[col_temp]
In [50]:
temp.head()
Out[50]:
In [51]:
temp.hist(bins = 15, figsize = (12, 16))
Out[51]:
In [ ]:
Exercise 6¶
In [ ]:
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px
In [ ]:
data = pd.read_csv('https://raw.githubusercontent.com/PacktWorkshops/The-Data-Analysis-Workshop/master/Chapter09/Datasets/energydata_complete.csv')
In [3]:
data.head()
Out[3]:
In [4]:
data.isnull().sum()
Out[4]:
In [ ]:
df1 = data.rename(columns = {
'date' : 'date_time',
'Appliances' : 'a_energy',
'lights' : 'l_energy',
'T1' : 'kitchen_temp',
'RH_1' : 'kitchen_hum',
'T2' : 'liv_temp',
'RH_2' : 'liv_hum',
'T3' : 'laun_temp',
'RH_3' : 'laun_hum',
'T4' : 'off_temp',
'RH_4' : 'off_hum',
'T5' : 'bath_temp',
'RH_5' : 'bath_hum',
'T6' : 'out_b_temp',
'RH_6' : 'out_b_hum',
'T7' : 'iron_temp',
'RH_7' : 'iron_hum',
'T8' : 'teen_temp',
'RH_8' : 'teen_hum',
'T9' : 'par_temp',
'RH_9' : 'par_hum',
'T_out' : 'out_temp',
'Press_mm_hg' : 'out_press',
'RH_out' : 'out_hum',
'Windspeed' : 'wind',
'Visibility' : 'visibility',
'Tdewpoint' : 'dew_point',
'rv1' : 'rv1',
'rv2' : 'rv2'
})
In [6]:
df1.head()
Out[6]:
In [7]:
df1.tail()
Out[7]:
In [8]:
df1.describe()
Out[8]:
In [9]:
lights_box = sns.boxplot(df1.l_energy)
In [ ]:
l = [0, 10, 20, 30, 40, 50, 60, 70]
In [ ]:
counts = []
In [ ]:
for i in l:
a = (df1.l_energy == i).sum()
counts.append(a)
In [13]:
counts
Out[13]:
In [14]:
lights = sns.barplot(x = l, y = counts)
lights.set_xlabel('Energy Consumed by Lights')
lights.set_ylabel('Number of Lights')
lights.set_title('Distribution of Energy Consumed by Lights')
Out[14]:
In [15]:
((df1.l_energy == 0).sum() / (df1.shape[0])) * 100
Out[15]:
In [ ]:
new_data = df1
In [ ]:
new_data.drop(['l_energy'], axis = 1, inplace = True)
In [18]:
new_data.head()
Out[18]:
In [19]:
app_box = sns.boxplot(new_data.a_energy)
In [20]:
out = (new_data['a_energy'] > 200).sum()
out
Out[20]:
In [21]:
(out/19735) * 100
Out[21]:
In [22]:
out_e = (new_data['a_energy'] > 950).sum()
out_e
Out[22]:
In [23]:
(out_e/19735) * 100
Out[23]:
In [ ]:
energy = new_data[(new_data['a_energy'] <= 200)]
In [25]:
energy.describe()
Out[25]:
In [ ]:
new_en = energy
In [ ]:
new_en['date_time'] = pd.to_datetime(new_en.date_time, format = '%Y-%m-%d %H:%M:%S')
In [28]:
new_en.head()
Out[28]:
In [ ]:
new_en.insert(loc = 1, column = 'month', value = new_en.date_time.dt.month)
In [ ]:
new_en.insert(loc = 2, column = 'day', value = (new_en.date_time.dt.dayofweek)+1)
In [31]:
new_en.head()
Out[31]:
In [ ]:
import plotly.graph_objs as go
In [ ]:
app_date = go.Scatter(x = new_en.date_time, mode = "lines", y = new_en.a_energy)
In [ ]:
layout = go.Layout(title = 'Appliance Energy Consumed by Date', xaxis = dict(title='Date'), yaxis = dict(title='Wh'))
In [ ]:
fig = go.Figure(data = [app_date], layout = layout)
In [37]:
fig.show()
In [ ]:
app_mon = new_en.groupby(by = ['month'], as_index = False)['a_energy'].sum()
In [39]:
app_mon
Out[39]:
In [40]:
app_mon.sort_values(by = 'a_energy', ascending = False).head()
Out[40]:
In [44]:
plt.subplots(figsize = (15, 6))
am = sns.barplot(app_mon.month, app_mon.a_energy)
plt.xlabel('Month')
plt.ylabel('Energy Consumed by Appliances')
plt.title('Total Energy Consumed by Appliances per Month')
plt.show()
In [45]:
app_day = new_en.groupby(by = ['day'], as_index = False)['a_energy'].sum()
app_day
Out[45]:
In [46]:
app_day.sort_values(by = 'a_energy', ascending = False)
Out[46]:
In [47]:
plt.subplots(figsize = (15, 6))
ad = sns.barplot(app_day.day, app_day.a_energy)
plt.xlabel('Day of the Week')
plt.ylabel('Energy Consumed by Appliances')
plt.title('Total Energy Consumed by Appliances')
plt.show()
In [ ]:
col_temp = ['kitchen_temp', 'liv_temp', 'laun_temp', 'off_temp',
'bath_temp', 'out_b_temp', 'iron_temp', 'teen_temp', 'par_temp']
In [ ]:
temp = new_en[col_temp]
In [50]:
temp.head()
Out[50]:
In [51]:
temp.hist(bins = 15, figsize = (12, 16))
Out[51]:
In [ ]:
col_hum = ['kitchen_hum', 'liv_hum', 'laun_hum', 'off_hum', 'bath_hum', 'out_b_hum', 'iron_hum', 'teen_hum', 'par_hum']
In [ ]:
hum = new_en[col_hum]
In [54]:
hum.head()
Out[54]:
In [55]:
hum.hist(bins = 15, figsize = (12, 16))
Out[55]:
In [56]:
col_weather = ["out_temp", "dew_point", "out_hum", "out_press",
"wind", "visibility"]
weath = new_en[col_weather]
weath.head()
weath.hist(bins = 15, figsize = (12, 16))
Out[56]:
Exercise 9.06: Plotting out_b, out_hum, visibility, and wind
In [58]:
f, ax = plt.subplots(2, 2, figsize = (12, 8))
obh = sns.distplot(hum["out_b_hum"], bins = 10, ax = ax[0][0])
oh = sns.distplot(weath["out_hum"], bins = 10, ax = ax[0][1])
vis = sns.distplot(weath["visibility"], bins = 10, ax = ax[1][0])
wind = sns.distplot(weath["wind"], bins = 10, ax = ax[1][1])
In [60]:
corr = new_en.corr()
mask = np.zeros_like(corr, dtype=np.bool)
mask[np.triu_indices_from(mask)] = True
f, ax = plt.subplots(figsize=(16, 14))
sns.heatmap(corr, annot = True, fmt = ".2f", mask = mask)
plt.xticks(range(len(corr.columns)), corr.columns)
plt.yticks(range(len(corr.columns)), corr.columns)
plt.show()
In [ ]:
Activity 1¶
In [ ]:
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px
In [ ]:
data = pd.read_csv('https://raw.githubusercontent.com/PacktWorkshops/The-Data-Analysis-Workshop/master/Chapter09/Datasets/energydata_complete.csv')
In [3]:
data.head()
Out[3]:
In [4]:
data.isnull().sum()
Out[4]:
In [ ]:
df1 = data.rename(columns = {
'date' : 'date_time',
'Appliances' : 'a_energy',
'lights' : 'l_energy',
'T1' : 'kitchen_temp',
'RH_1' : 'kitchen_hum',
'T2' : 'liv_temp',
'RH_2' : 'liv_hum',
'T3' : 'laun_temp',
'RH_3' : 'laun_hum',
'T4' : 'off_temp',
'RH_4' : 'off_hum',
'T5' : 'bath_temp',
'RH_5' : 'bath_hum',
'T6' : 'out_b_temp',
'RH_6' : 'out_b_hum',
'T7' : 'iron_temp',
'RH_7' : 'iron_hum',
'T8' : 'teen_temp',
'RH_8' : 'teen_hum',
'T9' : 'par_temp',
'RH_9' : 'par_hum',
'T_out' : 'out_temp',
'Press_mm_hg' : 'out_press',
'RH_out' : 'out_hum',
'Windspeed' : 'wind',
'Visibility' : 'visibility',
'Tdewpoint' : 'dew_point',
'rv1' : 'rv1',
'rv2' : 'rv2'
})
In [6]:
df1.head()
Out[6]:
In [7]:
df1.tail()
Out[7]:
In [8]:
df1.describe()
Out[8]:
In [9]:
lights_box = sns.boxplot(df1.l_energy)
In [ ]:
l = [0, 10, 20, 30, 40, 50, 60, 70]
In [ ]:
counts = []
In [ ]:
for i in l:
a = (df1.l_energy == i).sum()
counts.append(a)
In [13]:
counts
Out[13]:
In [14]:
lights = sns.barplot(x = l, y = counts)
lights.set_xlabel('Energy Consumed by Lights')
lights.set_ylabel('Number of Lights')
lights.set_title('Distribution of Energy Consumed by Lights')
Out[14]:
In [15]:
((df1.l_energy == 0).sum() / (df1.shape[0])) * 100
Out[15]:
In [ ]:
new_data = df1
In [ ]:
new_data.drop(['l_energy'], axis = 1, inplace = True)
In [18]:
new_data.head()
Out[18]:
Activity 9.01
In [19]:
app_box = sns.boxplot(new_data.a_energy)
In [20]:
out = (new_data['a_energy'] > 200).sum()
out
Out[20]:
In [21]:
(out/19735) * 100
Out[21]:
In [22]:
out_e = (new_data['a_energy'] > 950).sum()
out_e
Out[22]:
In [23]:
(out_e/19735) * 100
Out[23]:
In [ ]:
energy = new_data[(new_data['a_energy'] <= 200)]
In [25]:
energy.describe()
Out[25]:
In [ ]:
Activity 2¶
In [ ]:
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px
In [ ]:
data = pd.read_csv('https://raw.githubusercontent.com/PacktWorkshops/The-Data-Analysis-Workshop/master/Chapter09/Datasets/energydata_complete.csv')
In [3]:
data.head()
Out[3]:
In [4]:
data.isnull().sum()
Out[4]:
In [ ]:
df1 = data.rename(columns = {
'date' : 'date_time',
'Appliances' : 'a_energy',
'lights' : 'l_energy',
'T1' : 'kitchen_temp',
'RH_1' : 'kitchen_hum',
'T2' : 'liv_temp',
'RH_2' : 'liv_hum',
'T3' : 'laun_temp',
'RH_3' : 'laun_hum',
'T4' : 'off_temp',
'RH_4' : 'off_hum',
'T5' : 'bath_temp',
'RH_5' : 'bath_hum',
'T6' : 'out_b_temp',
'RH_6' : 'out_b_hum',
'T7' : 'iron_temp',
'RH_7' : 'iron_hum',
'T8' : 'teen_temp',
'RH_8' : 'teen_hum',
'T9' : 'par_temp',
'RH_9' : 'par_hum',
'T_out' : 'out_temp',
'Press_mm_hg' : 'out_press',
'RH_out' : 'out_hum',
'Windspeed' : 'wind',
'Visibility' : 'visibility',
'Tdewpoint' : 'dew_point',
'rv1' : 'rv1',
'rv2' : 'rv2'
})
In [6]:
df1.head()
Out[6]:
In [7]:
df1.tail()
Out[7]:
In [8]:
df1.describe()
Out[8]:
In [9]:
lights_box = sns.boxplot(df1.l_energy)
In [ ]:
l = [0, 10, 20, 30, 40, 50, 60, 70]
In [ ]:
counts = []
In [ ]:
for i in l:
a = (df1.l_energy == i).sum()
counts.append(a)
In [13]:
counts
Out[13]:
In [14]:
lights = sns.barplot(x = l, y = counts)
lights.set_xlabel('Energy Consumed by Lights')
lights.set_ylabel('Number of Lights')
lights.set_title('Distribution of Energy Consumed by Lights')
Out[14]:
In [15]:
((df1.l_energy == 0).sum() / (df1.shape[0])) * 100
Out[15]:
In [ ]:
new_data = df1
In [ ]:
new_data.drop(['l_energy'], axis = 1, inplace = True)
In [18]:
new_data.head()
Out[18]:
In [19]:
app_box = sns.boxplot(new_data.a_energy)
In [20]:
out = (new_data['a_energy'] > 200).sum()
out
Out[20]:
In [21]:
(out/19735) * 100
Out[21]:
In [22]:
out_e = (new_data['a_energy'] > 950).sum()
out_e
Out[22]:
In [23]:
(out_e/19735) * 100
Out[23]:
In [ ]:
energy = new_data[(new_data['a_energy'] <= 200)]
In [25]:
energy.describe()
Out[25]:
In [ ]:
new_en = energy
In [ ]:
new_en['date_time'] = pd.to_datetime(new_en.date_time, format = '%Y-%m-%d %H:%M:%S')
In [28]:
new_en.head()
Out[28]:
In [ ]:
new_en.insert(loc = 1, column = 'month', value = new_en.date_time.dt.month)
In [ ]:
new_en.insert(loc = 2, column = 'day', value = (new_en.date_time.dt.dayofweek)+1)
In [31]:
new_en.head()
Out[31]:
In [ ]:
import plotly.graph_objs as go
In [ ]:
app_date = go.Scatter(x = new_en.date_time, mode = "lines", y = new_en.a_energy)
In [ ]:
layout = go.Layout(title = 'Appliance Energy Consumed by Date', xaxis = dict(title='Date'), yaxis = dict(title='Wh'))
In [ ]:
fig = go.Figure(data = [app_date], layout = layout)
In [37]:
fig.show()
In [ ]:
app_mon = new_en.groupby(by = ['month'], as_index = False)['a_energy'].sum()
In [39]:
app_mon
Out[39]:
In [40]:
app_mon.sort_values(by = 'a_energy', ascending = False).head()
Out[40]:
In [44]:
plt.subplots(figsize = (15, 6))
am = sns.barplot(app_mon.month, app_mon.a_energy)
plt.xlabel('Month')
plt.ylabel('Energy Consumed by Appliances')
plt.title('Total Energy Consumed by Appliances per Month')
plt.show()
Activity 9.02
In [45]:
app_day = new_en.groupby(by = ['day'], as_index = False)['a_energy'].sum()
app_day
Out[45]:
In [46]:
app_day.sort_values(by = 'a_energy', ascending = False)
Out[46]:
In [47]:
plt.subplots(figsize = (15, 6))
ad = sns.barplot(app_day.day, app_day.a_energy)
plt.xlabel('Day of the Week')
plt.ylabel('Energy Consumed by Appliances')
plt.title('Total Energy Consumed by Appliances')
plt.show()
In [ ]:
Activity 3¶
In [ ]:
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import plotly.express as px
In [ ]:
data = pd.read_csv('https://raw.githubusercontent.com/PacktWorkshops/The-Data-Analysis-Workshop/master/Chapter09/Datasets/energydata_complete.csv')
In [3]:
data.head()
Out[3]:
In [4]:
data.isnull().sum()
Out[4]:
In [ ]:
df1 = data.rename(columns = {
'date' : 'date_time',
'Appliances' : 'a_energy',
'lights' : 'l_energy',
'T1' : 'kitchen_temp',
'RH_1' : 'kitchen_hum',
'T2' : 'liv_temp',
'RH_2' : 'liv_hum',
'T3' : 'laun_temp',
'RH_3' : 'laun_hum',
'T4' : 'off_temp',
'RH_4' : 'off_hum',
'T5' : 'bath_temp',
'RH_5' : 'bath_hum',
'T6' : 'out_b_temp',
'RH_6' : 'out_b_hum',
'T7' : 'iron_temp',
'RH_7' : 'iron_hum',
'T8' : 'teen_temp',
'RH_8' : 'teen_hum',
'T9' : 'par_temp',
'RH_9' : 'par_hum',
'T_out' : 'out_temp',
'Press_mm_hg' : 'out_press',
'RH_out' : 'out_hum',
'Windspeed' : 'wind',
'Visibility' : 'visibility',
'Tdewpoint' : 'dew_point',
'rv1' : 'rv1',
'rv2' : 'rv2'
})
In [6]:
df1.head()
Out[6]:
In [7]:
df1.tail()
Out[7]:
In [8]:
df1.describe()
Out[8]:
In [9]:
lights_box = sns.boxplot(df1.l_energy)
In [ ]:
l = [0, 10, 20, 30, 40, 50, 60, 70]
In [ ]:
counts = []
In [ ]:
for i in l:
a = (df1.l_energy == i).sum()
counts.append(a)
In [13]:
counts
Out[13]:
In [14]:
lights = sns.barplot(x = l, y = counts)
lights.set_xlabel('Energy Consumed by Lights')
lights.set_ylabel('Number of Lights')
lights.set_title('Distribution of Energy Consumed by Lights')
Out[14]:
In [15]:
((df1.l_energy == 0).sum() / (df1.shape[0])) * 100
Out[15]:
In [ ]:
new_data = df1
In [ ]:
new_data.drop(['l_energy'], axis = 1, inplace = True)
In [18]:
new_data.head()
Out[18]:
In [19]:
app_box = sns.boxplot(new_data.a_energy)
In [20]:
out = (new_data['a_energy'] > 200).sum()
out
Out[20]:
In [21]:
(out/19735) * 100
Out[21]:
In [22]:
out_e = (new_data['a_energy'] > 950).sum()
out_e
Out[22]:
In [23]:
(out_e/19735) * 100
Out[23]:
In [ ]:
energy = new_data[(new_data['a_energy'] <= 200)]
In [25]:
energy.describe()
Out[25]:
In [ ]:
new_en = energy
In [ ]:
new_en['date_time'] = pd.to_datetime(new_en.date_time, format = '%Y-%m-%d %H:%M:%S')
In [28]:
new_en.head()
Out[28]:
In [ ]:
new_en.insert(loc = 1, column = 'month', value = new_en.date_time.dt.month)
In [ ]:
new_en.insert(loc = 2, column = 'day', value = (new_en.date_time.dt.dayofweek)+1)
In [31]:
new_en.head()
Out[31]:
In [ ]:
import plotly.graph_objs as go
In [ ]:
app_date = go.Scatter(x = new_en.date_time, mode = "lines", y = new_en.a_energy)
In [ ]:
layout = go.Layout(title = 'Appliance Energy Consumed by Date', xaxis = dict(title='Date'), yaxis = dict(title='Wh'))
In [ ]:
fig = go.Figure(data = [app_date], layout = layout)
In [37]:
fig.show()
In [ ]:
app_mon = new_en.groupby(by = ['month'], as_index = False)['a_energy'].sum()
In [39]:
app_mon
Out[39]:
In [40]:
app_mon.sort_values(by = 'a_energy', ascending = False).head()
Out[40]:
In [44]:
plt.subplots(figsize = (15, 6))
am = sns.barplot(app_mon.month, app_mon.a_energy)
plt.xlabel('Month')
plt.ylabel('Energy Consumed by Appliances')
plt.title('Total Energy Consumed by Appliances per Month')
plt.show()
In [45]:
app_day = new_en.groupby(by = ['day'], as_index = False)['a_energy'].sum()
app_day
Out[45]:
In [46]:
app_day.sort_values(by = 'a_energy', ascending = False)
Out[46]:
In [47]:
plt.subplots(figsize = (15, 6))
ad = sns.barplot(app_day.day, app_day.a_energy)
plt.xlabel('Day of the Week')
plt.ylabel('Energy Consumed by Appliances')
plt.title('Total Energy Consumed by Appliances')
plt.show()
In [ ]:
col_temp = ['kitchen_temp', 'liv_temp', 'laun_temp', 'off_temp',
'bath_temp', 'out_b_temp', 'iron_temp', 'teen_temp', 'par_temp']
In [ ]:
temp = new_en[col_temp]
In [50]:
temp.head()
Out[50]:
In [51]:
temp.hist(bins = 15, figsize = (12, 16))
Out[51]:
Activity 9.03
In [ ]:
col_hum = ['kitchen_hum', 'liv_hum', 'laun_hum', 'off_hum', 'bath_hum', 'out_b_hum', 'iron_hum', 'teen_hum', 'par_hum']
In [ ]:
hum = new_en[col_hum]
In [54]:
hum.head()
Out[54]:
In [55]:
hum.hist(bins = 15, figsize = (12, 16))
Out[55]:
In [56]:
col_weather = ["out_temp", "dew_point", "out_hum", "out_press",
"wind", "visibility"]
weath = new_en[col_weather]
weath.head()
weath.hist(bins = 15, figsize = (12, 16))
Out[56]: